Recurrent machines for likelihood-free inference

TL;DR

This paper introduces a recurrent inference machine that uses meta-learning to automatically learn an iterative optimization process for likelihood-free inference, showing promising results on toy simulators.

Contribution

It proposes a novel recurrent inference machine that learns to perform likelihood-free inference without explicit divergence measures, advancing automated parameter estimation.

Findings

Shows promising results on toy simulators

Demonstrates robustness and performance improvements

Introduces a new meta-learning approach for likelihood-free inference

Abstract

Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations. In the absence of a likelihood function, most of the existing inference methods optimize the simulator parameters through a handcrafted iterative procedure that tries to make the simulated data more similar to the observations. In this work, we explore whether meta-learning can be used in the likelihood-free context, for learning automatically from data an iterative optimization procedure that would solve likelihood-free inference problems. We design a recurrent inference machine that learns a sequence of parameter updates leading to good parameter estimates, without ever specifying some explicit notion of divergence between the simulated data and the real data distributions. We demonstrate our approach on toy simulators, showing promising results both in terms of performance and robustness.